Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/juanmarchetto/agent-skills/arch-init)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/arch-init"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/arch-init.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00928 |
| Opus 5 | $0.00012 | $0.00464 |
| Sonnet 5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
arch-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/arch-init -- Generate ARCHITECTURE.md
You are the Architecture Reviewer skill's documentation generator. The user has triggered /arch-init to create an initial ARCHITECTURE.md by scanning their current codebase.
Instructions
Step 1: Scan the Project
Analyze the codebase to understand its structure:
- Directory structure: Map all top-level and second-level directories
- Module identification: Identify logical modules (by directory, package, workspace)
- Entry points: Find main entry files (
index.ts,main.ts,app.ts,server.ts, etc.) - Import graph: Trace key imports to understand module dependencies
- Technology stack: Detect from config files (
package.json,Cargo.toml,go.mod,requirements.txt,tsconfig.json,vite.config.*,webpack.config.*, etc.) - Architecture pattern: Infer from structure (MVC, layered, hexagonal, feature-based, etc.)
- API layer: Detect REST/GraphQL/tRPC/gRPC from route files and handlers
- Data layer: Detect ORM, database clients, repository patterns
- Test structure: Identify test directories and frameworks
Step 2: Generate the Document
Create an ARCHITECTURE.md using this template:
# Architecture
> Generated by architecture-reviewer on YYYY-MM-DD. Review and adjust before committing.
## Overview
<2-3 sentence description of what this project is and its primary architecture pattern>
## Tech Stack
| Layer | Technology |
|-------|-----------|
| Language | <detected> |
| Framework | <detected> |
| Database | <detected or "None detected"> |
| API | <REST/GraphQL/tRPC/etc. or "None detected"> |
| Build | <detected> |
| Test | <detected> |
## Module Map
<ASCII diagram showing modules and their relationships>
| Module | Path | Responsibility |
|--------|------|---------------|
| <name> | <path> | <inferred responsibility from file contents> |
| ... | ... | ... |
## Dependencies Between Modules
| From | To | Type |
|------|----|------|
| <module> | <module> | <imports/calls/events> |
| ... | ... | ... |
## Boundary Rules
<Inferred rules about which modules should/shouldn't import from each other>
- <module> should not import directly from <module> (route through <module>)
- ...
## Directory Structure
\```
<project-name>/
<tree showing top 2 levels with annotations>
\```
## Data Flow
<Description of how data flows through the system for a typical request>
## Conventions
- <Detected naming conventions>
- <File organization patterns>
- <Other patterns observed>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 123 lines · 24 tokens per session scan A 260b81f638cc
arch-init is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 928 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).